{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZBUVYI2W4DWCMWZXP3UQ5XR6CJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e3279e44f5b227c5cf0cf6ef66d52a87329b08fc548ad9a5dec0d4ecd77a2866","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:13:44Z","title_canon_sha256":"a4693d03039ed1ebdf3c40340b89ee45e9a20b4df0e5069a6ee57b584638b8d0"},"schema_version":"1.0","source":{"id":"2305.17011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17011","created_at":"2026-07-05T06:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17011v1","created_at":"2026-07-05T06:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17011","created_at":"2026-07-05T06:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZBUVYI2W4DWC","created_at":"2026-07-05T06:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZBUVYI2W4DWCMWZX","created_at":"2026-07-05T06:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZBUVYI2W","created_at":"2026-07-05T06:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:3805c7b61f5e5de7e2f6f2a1e98d9f15aacbd9feb7ca18e2b2a6bdc6b7aaf553","target":"graph","created_at":"2026-07-05T06:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.17011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for each frame separately. However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for un","authors_text":"Shuyan Li, Xiu Li, Yansong Tang, Yicheng Xiao, Yitong Wang, Yong Liu, Yujiu Yang, Zhuoyan Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:13:44Z","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17011","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6fbe2bd7b5955d9671750cf06c333e1d2367c363f8acc40607898d2176539b36","target":"record","created_at":"2026-07-05T06:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e3279e44f5b227c5cf0cf6ef66d52a87329b08fc548ad9a5dec0d4ecd77a2866","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:13:44Z","title_canon_sha256":"a4693d03039ed1ebdf3c40340b89ee45e9a20b4df0e5069a6ee57b584638b8d0"},"schema_version":"1.0","source":{"id":"2305.17011","kind":"arxiv","version":1}},"canonical_sha256":"c8695c2356e0ec265b377ee90ede3e127ac08f9854e76b0295ffd5f6ec053c57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8695c2356e0ec265b377ee90ede3e127ac08f9854e76b0295ffd5f6ec053c57","first_computed_at":"2026-07-05T06:14:20.046862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:20.046862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDBOLeW4wJvG3KNYNE5ThOymaSdkZfG71FYqVgys9kuOayW59Ul6skgdokBYA6rVXtDkRe3BTOikARQtrfdVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:20.047197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fbe2bd7b5955d9671750cf06c333e1d2367c363f8acc40607898d2176539b36","sha256:3805c7b61f5e5de7e2f6f2a1e98d9f15aacbd9feb7ca18e2b2a6bdc6b7aaf553"],"state_sha256":"0a792f3cb0dcd8dc9de2233d5efe18a98dba184a66fe574e224d34691210fe9b"}